Automated detection and repositioning of micro-objects in microfluidic devices

Abstract

Methods are provided for the automated detection and/or counting of micro-objects in a microfluidic device. In addition, methods are provided for repositioning micro-objects in a microfluidic device. In addition, methods are provided for separating micro-objects in a spatial region of the microfluidic device.

1 .- 78 . (canceled) 
     
     
         79 . A system for automatically detecting and repositioning micro-objects disposed within a microfluidic device, the system comprising:
 an image acquisition unit, comprising:
 an imaging element configured to capture one or more images of a microfluidic device, and 
 an image pre-processing engine configured to reduce anomalies in the image data; and 
   a micro-object detection unit communicatively connected to the image acquisition unit, comprising:
 a neural network configured to annotate pixel data in an image according to a plurality of micro-object characteristics and output probability values for each pixel in the pixel data; 
 a threshold engine configured to determine which pixel probabilities at least meet a defined threshold, and 
 a detection engine configured to apply image post-processing techniques and output a micro-object count. 
   
     
     
         80 . The system of  claim 79 , wherein said micro-object detection unit is configured to generate a plurality of pixel masks from image data derived from an image obtained by the image acquisition unit. 
     
     
         81 . The system of  claim 80 , wherein each pixel mask comprises a set of pixel annotations, each pixel annotation of the set representing a probability that a corresponding pixel in the image represents the corresponding micro-object characteristic. 
     
     
         82 . The system of  claim 79 , wherein the plurality of micro-object characteristics comprises at least one of: (i) micro-object center; (ii) micro-object edge; and (iii) non-micro-object. 
     
     
         83 . The system of  claim 79 , wherein obtaining a micro-object count comprises obtaining a micro-object count from the pixel mask corresponding to the micro-object center characteristics or a combination of pixel masks that includes the pixel mask corresponding to the micro-object center characteristic. 
     
     
         84 . The system of  claim 79 , further comprising a motive module, wherein said motive module is communicatively coupled to the image acquisition unit and the micro-object detection unit. 
     
     
         85 . The system of  claim 84 , wherein said motive module is configured to generate a force in proximity to at least one micro-object of the plurality of micro-objects counted by the micro-object detection unit. 
     
     
         86 . The system of  claim 85 , wherein said motive module is further configured to move the force to a specified spatial region of the microfluidic device to thereby reposition the first micro-object. 
     
     
         87 . A method of re-positioning micro-objects in a microfluidic device comprising a plurality of sequestration pens, the method comprising:
 identifying a set of micro-objects disposed within the microfluidic device, wherein the set of micro-objects is identified by generating a plurality of pixel masks from the image for a corresponding plurality of micro-object characteristics, wherein generating the plurality of pixel masks comprises processing pixel data from the image using a machine learning algorithm, and wherein each pixel mask comprises a set of pixel annotations, each pixel annotation of the set representing a probability that a corresponding pixel in the image represents the corresponding micro-object characteristic;   
       computing one or more trajectories, wherein each trajectory is a path that connects one micro-object of the set of micro-objects with one sequestration pen of the plurality of sequestration pens;
 selecting, for one or more micro-objects of the set of micro-objects, a trajectory from the one or more trajectories; and 
 re-positioning at least one micro-object of the one or more micro-objects having a selected trajectory by moving the micro-object along its selected trajectory. 
 
     
     
         88 . The method of  claim 87 , wherein the plurality of micro-object characteristics comprises at least three micro-object characteristics, and the plurality of micro-object characteristics comprises at least: (i) micro-object center; (ii) micro-object edge; and (iii) non-micro-object. 
     
     
         89 . The method of  claim 87 , wherein identifying a set of micro-objects disposed within the microfluidic device further comprises: obtaining a micro-object count comprises obtaining a micro-object count from the pixel mask corresponding to the micro-object center characteristic or a combination of pixel masks that includes the pixel mask corresponding to the micro-object center characteristic. 
     
     
         90 . The method of  claim 87 , wherein the machine learning algorithm comprises a neural network. 
     
     
         91 . The method of any one of  claim 87  further comprising pre-processing the image prior to generating the plurality of pixel masks. 
     
     
         92 . The method of  claim 91 , wherein the micro-objects are imaged within a microfluidic device, and wherein the pre-processing comprises subtracting out a repeating pattern produced by at least one component of the microfluidic device during imaging. 
     
     
         93 . The method of  claim 92 , wherein the pre-processing comprises applying a Fourier transform to the image to identify the repeating pattern. 
     
     
         94 . The method of  claim 93 , wherein the at least one component of the microfluidic device is a substrate surface comprising a photo-transistor array. 
     
     
         95 . The method of  claim 91 , wherein pre-processing the image comprises flipping and/or rotating the image into a desired orientation. 
     
     
         96 . The method of  claim 91 , wherein pre-processing the image comprises leveling brightness across the image using a polynomial best-fit correction. 
     
     
         97 . The method of  claim 91 , wherein pre-processing the image comprises correcting for distortion introduced in the image during the imaging process. 
     
     
         98 . The method of  claim 90 , further comprising: training the neural network using a set of training images that contain micro-objects. 
     
     
         99 . The method of  claim 87  wherein identifying a set of micro-objects further comprises classifying the micro-objects identified in the micro-object count into at least one of a plurality of micro-object types. 
     
     
         100 . The method of  claim 87 , wherein the micro-objects are biological cells. 
     
     
         101 . The method of  claim 100 , wherein the biological cells are immunological cells, cancer cells, cells from a cell line, oocytes, sperm, or embryos.